Spatial Analysis
Read Data
You must read the data before trying to run code on your own machine. To read data use the following code after setting your working directory. To set your working directory, modify the following to set the file path for the folder where the data file resides. setwd(’c:/thatawesomeclass/)
Here is AirBnb data on rentals in New York city for a couple of months. Since the data contains locations of the rentals, this is spatial data. The features of each rental are related to a single location, therefore this is called point data.
data = read.csv('analysisData_with_lonlat.csv')Visualize airbnb data
What does the plot look like?
library(ggplot2)
ggplot(data) +
geom_point(aes(x=longitude,y=latitude),size=0.1)
Mapping Data using Google Maps
Google API Data
Google has recently changed its API requirements, and ggmap users are now required to provide an API key and enable billing. ggmap itself is outdated on CRAN. Until the new version is available on CRAN, you can install an updated version by running the following code
# if(!requireNamespace("devtools")) install.packages("devtools")
# devtools::install_github("dkahle/ggmap", ref = "tidyup")When you load ggmap, you can set your API key with register_google() (see ?register_google for details), but don’t forget to enable the Maps Static API in the Google Cloud interface and enable billing!
For you to use the google maps code below you will have to get your own api from Google. Once you have obtained an api key, you can assign it to the object api_key.
library(ggmap)
register_google(key = api_key)Map of New York
Get map of New York City by setting location as center of the city.
library(ggmap)
newyork_map = get_map(location=c(-73.93,40.77), zoom=10, scale=4)
ggmap(newyork_map)
Add a data layer: Map of New York City + AirBnb Rentals
ggmap(newyork_map)+
geom_point(data=data, aes(x=longitude,y=latitude), size=0.1)
Address overplotting by setting alpha=0.2, and change the color of rental location to seagreen
ggmap(newyork_map)+
geom_point(data=data, aes(x=longitude,y=latitude), size=0.1, alpha=0.2, color='seagreen')
Map of New York city + AirBnb rentals + price
Represent price using Yellow-orange-red scale
library(RColorBrewer)
ggmap(newyork_map)+
geom_point(data=data, aes(x=longitude,y=latitude,color=price), size=0.1, alpha=0.2)+
scale_color_gradientn(colors=brewer.pal(n=7, name='YlOrRd'))
Satellite Map of Manhattan
manhattan = get_map(location=c(-73.93,40.77), zoom=12, scale=4, maptype='satellite')
ggmap(manhattan)
Manhattan (Satellite) + Rentals + Price
Price is being converted into five percentile bins to make it easier to spot location differences in price.
library(Hmisc)
ggmap(manhattan)+
geom_point(data=data, aes(x=longitude,y=latitude,color=cut2(data$price,g=5)), size=0.3)+
scale_color_brewer(type ='seq', palette='RdYlGn', direction=-1)
Toner Map of Manhattan
Sometimes, all we want is a simple old fashioned map.
manhattan = get_map(location=c(-73.93,40.77), zoom=12, scale=4, maptype='toner')
ggmap(manhattan)
Manhattan (Toner) + Rentals + Price
ggmap(manhattan)+
geom_point(data=data, aes(x=longitude,y=latitude,color=cut2(data$price,g=5)), size=0.3)+
scale_color_brewer(type='seq', palette='RdYlGn', direction =-1)
Terrain Map of Manhattan
manhattan = get_map(location=c(-73.93,40.77), zoom=12, scale=4, maptype='terrain', source='stamen')
ggmap(manhattan)